© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13051
    Prev
    Next
    INDEX
    Explanations

    helper or linking verbs (is, was, has, have, be) or prepositions (in, for, with, into) near pronouns or numbers

    oai_token-act-pair · gemini-2.0-flash

    technical documentation/forums

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zenberg
    -0.41
    فسير
    -0.41
    至於
    -0.41
    ribune
    -0.40
     собою
    -0.40
    TypedValue
    -0.40
    rantes
    -0.40
    mão
    -0.39
    reinterpret
    -0.38
     {@
    -0.38
    POSITIVE LOGITS
     doInBackground
    0.85
     المعيارى
    0.79
    ftagPool
    0.77
    RTGC
    0.72
    +#+#
    0.71
     Италијани
    0.71
    忑
    0.68
     autorytatywna
    0.66
    VersionUID
    0.66
    webElementGuid
    0.65
    Activations Density 1.084%

    No Known Activations